© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208789
    Prev
    Next
    INDEX
    Explanations

    travel destinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_19_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhythm
    0.40
     former
    0.39
    duration
    0.38
     -\
    0.37
    former
    0.37
     şöyle
    0.37
    다고
    0.36
    following
    0.36
    rough
    0.35
     rhythms
    0.35
    POSITIVE LOGITS
    和服务
    0.42
    朿
    0.39
     որ
    0.38
    帅
    0.38
     बाजार
    0.38
    ഴി
    0.37
    界
    0.37
    вана
    0.36
    িয়ার
    0.36
     ભારત
    0.36
    Activations Density 0.006%

    No Known Activations